Stars
The world's simplest facial recognition api for Python and the command line
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Anbox is a container-based approach to boot a full Android system on a regular GNU/Linux system
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
Keras implementation of RetinaNet object detection.
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
pytorch tutorial for beginners
MOT using deepsort and yolov3 with pytorch
A collection of awesome resources in Human Pose estimation.
Implementation of Convolutional LSTM in PyTorch.
Notes on the Deep Learning book from Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016)
Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).
Data science interview questions with answers. Not ideally (yet)
Human Pose estimation with TensorFlow framework
shell scripts to install different version of OpenCV in different distributions of Linux
A mobilenet SSD based face detector, powered by tensorflow object detection api, trained by WIDERFACE dataset.
Arbitrary object tracking at 50-100 FPS with Fully Convolutional Siamese networks.
🚀 😏 Near Real Time CPU Face detection using deep learning
Quickly add MediaPipe Pose Estimation and Detection to your iOS app. Enable powerful features in your app powered by the body or hand.
Easy Real time gender age prediction from webcam video with Keras
Gate-Shift Networks for Video Action Recognition - CVPR 2020
Lightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]
This repo contains code to convert Structured Documents to Graphs and implement a Graph Convolution Neural Network for node classification
Video Predicting using ConvLSTM and pytorch
My Docker scripts and Dockerfile for several frameworks.